Metraipolis › archive › dc_2bd86a96caf7
WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation — arXiv:2608.09298
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09298
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:12:45.705Z
- SHA-256 of the archived text
dbbaeb49c43b944301304bc5e56b9afd5b526e3b3015d859170269789d0e5ccf- Stable URL of this page
https://metraipolis.com/documento/dc_2bd86a96caf7
How to cite
WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation — arXiv:2608.09298 — arXiv (en), https://arxiv.org/abs/2608.09298 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bd86a96caf7 (Metraipolis archive dc_2bd86a96caf7, sha256 dbbaeb49c43b944301304bc5e56b9afd5b526e3b3015d859170269789d0e5ccf)
BibTeX
@misc{dc2bd86a96caf7,
title = {WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation — arXiv:2608.09298},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09298},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bd86a96caf7; sha256 dbbaeb49c43b944301304bc5e56b9afd5b526e3b3015d859170269789d0e5ccf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09298. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Action-conditioned world models (ACWMs) promise to provide embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation. Realizing this promise requires precise action-conditioned transitions rather than merely plausible outputs. Yet their applicability remains difficult to establish because prevailing evaluations emphasize visual quality, task outcomes, or coarse rollout-level responsiveness without directly testing simulator fidelity. To address this gap, we evaluate ACWMs through the observable capabilities expected of physical simulators. Accordingly, we formalize Observable Simulator Contract, a minimal contract that any action-conditioned physical simulator should satisfy: supplied actions must induce corresponding agent motion, and environment responses must be grounded in that realized motion. To operationalize this contract, we introduce WorldSimProbe, comprising five controlled suites spanning local control sensitivity, global trajectory variation, source-diverse actions, interaction grounding, and dynamics. Suite-specific evaluators assess simulator-relative calibration, dense action-to-motion correspondence, false-interaction grounding, and primitive-level dynamics. We evaluate six open-source ACWMs on more than 18,000 instances across RoboTwin, ManiSkill, and LIBERO. World-SimProbe reveals systematic action-realization degradation across control variation, structured failures in interaction grounding and dynamics, and benchmark signals consistent with human judgments and downstream outcomes. Together, this capability-based framework provides a transparent, and standardized paradigm for diagnosing ACWM simulator fidelity beyond coarse, task-directed evaluation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.RO). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.09298 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T09:11:58.777Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).